© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4893
    Prev
    Next
    INDEX
    Explanations

    phrases related to death and grief

    oai_token-act-pair · gemini-2.0-flash

    heart, emotions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     onCancelled
    -0.63
     समीक्षाओं
    -0.62
    yntaxException
    -0.61
     Verso
    -0.56
    Халык
    -0.55
    GenerationType
    -0.55
    +#+
    -0.54
     المعيارى
    -0.53
    ftagPool
    -0.53
    HostException
    -0.52
    POSITIVE LOGITS
     heart
    0.89
    Heart
    0.82
     Heart
    0.82
    heart
    0.79
    HEART
    0.77
     HEART
    0.76
     hearts
    0.67
    Pain
    0.66
     déchir
    0.66
     corazón
    0.65
    Activations Density 2.906%

    No Known Activations